Detection of leukemia in microscopic white blood cell images

Khobragade, Shubhangi; Mor, Dheeraj Dilip; Patil, C. Y.

doi:10.1109/infop.2015.7489422

Cited by 40 publications

(18 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…White blood cells (WBCs) are important immune cells in the human body, which are mainly involved in immune response and regulation of inflammation [ 1 ]. The three-type differential count of WBCs, i.e., monocyte, lymphocyte, and granulocyte, provides an important indication for the diagnosis of many diseases, such as leukemia [ 2 , 3 ] and cancers [ 4 ]. As the dominant fraction of granulocytes, neutrophils usually show an abnormal change in the expected number when dealing with damaged tissues and unresolved infections [ 5 ].…”

Section: Introductionmentioning

confidence: 99%

Deep-Learning Based Label-Free Classification of Activated and Inactivated Neutrophils for Rapid Immune State Monitoring

Huang

Jeon

Liu

et al. 2021

Sensors

View full text Add to dashboard Cite

The differential count of white blood cells (WBCs) is one widely used approach to assess the status of a patient’s immune system. Currently, the main methods of differential WBC counting are manual counting and automatic instrument analysis with labeling preprocessing. But these two methods are complicated to operate and may interfere with the physiological states of cells. Therefore, we propose a deep learning-based method to perform label-free classification of three types of WBCs based on their morphologies to judge the activated or inactivated neutrophils. Over 90% accuracy was finally achieved by a pre-trained fine-tuning Resnet-50 network. This deep learning-based method for label-free WBC classification can tackle the problem of complex instrumental operation and interference of fluorescent labeling to the physiological states of the cells, which is promising for future point-of-care applications.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep-Learning Based Label-Free Classification of Activated and Inactivated Neutrophils for Rapid Immune State Monitoring

Huang

Jeon

Liu

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Khobragade et al [10] demonstrated a technique of leukaemia detection in patients from testing the microscopic white blood cell images. The focus is on the variations in the geometry of cells and statistical parameters such as mean and standard deviation which differentiates the white blood cells from other blood components employing processing tools including MATLAB and Lab VIEW.…”

Section: Literature Reviewmentioning

confidence: 99%

“…In the proposed research work, rather than making use of the BBPSO algorithm, Bare-bones with Adaptive Bat Optimization (BBABO) is introduced for feature selection process. At last, the classification task is carried out by integrating both the Fuzzy Neural Network (FNN) and Enhanced Support Vector Machine (ESVM) classifiers [10] called as FNESVM.…”

Section: Introductionmentioning

confidence: 99%

Enhanced Support Vector Machine Based Leukaemia Cancer Classification

Preethi*¹,

Maheswari²

2019

IJRTE

View full text Add to dashboard Cite

Leukaemia is a blood cancer that is characterized by the bone marrow’s unregulated and irregular generation of white blood cells (leukocytes) in the blood. By testing the microscopic blood cell images, diseases can be detected and its early diagnosis can be done. In the current work,at smart decision support systemutilizing microscopic images is proposedto make a diagnosisof acute lymphoblastic leukaemia. Identification through images is a quick and inexpensive technique since there is no equipment is specially needed for lab testing. The improved Bare-Bones Particle Swarm Optimization algorithm is usedto identify the important distinguishing featuresof blast cells and the healthy cells to help in carry out the acute lymphoblastic leukaemia classification with efficiency. To avoid the poor accuracy, the modified median filtering has been introduced in this novel, which helps in removing the noise from the images and maintains the edge which is used to improve the identification of leukocytes and lymphocytes during the segmentation process. Enhanced linear contrast stretching is introduced in image enhancement for enriching the image. In the next step, feature extraction is carried out through the second order statistical features. Bare-bones with Adaptive Bat Optimization (BBABO) is used for feature selection. At last, the classification is carried out by using the combined Fuzzy Neural Network (FNN) and here the Enhanced Support Vector Machine (ESVM) is a classifier called as FNESVM.

show abstract

“…Among thresholding methods, the Otsu's method is reported to be highly efficient. 5,6 An adaptive segmentation method for WBCs was proposed by Liu et al 7 This method utilizes the outstanding edge density and low intensity of WBCs to discriminate them from red blood cells. 7 Other than classic segmentation methods, classifiers are commonly used for direct detection of objects of interest.…”

Section: Introductionmentioning

confidence: 99%

DeepQuantify: deep learning and quantification system of white blood cells in light microscopy images of injured skeletal muscles

et al. 2019

View full text Add to dashboard Cite

White blood cells (WBCs) are the most diverse types of cells observed in the healing process of injured skeletal muscles. In the recovery process, WBCs exhibit a dynamic cellular response and undergo multiple changes of the protein expression. The progress of healing can be analyzed by the number of WBCs or by the number of specific proteins observed in light microscopy images obtained at different time points after injury. We propose a deep learning quantification and analysis system called DeepQuantify to analyze WBCs in light microscopy images of uninjured and injured muscles of female mice. The DeepQuantify system features in segmentation using the localized iterative Otsu's thresholding method, masking postprocessing, and classification of WBCs with a convolutional neural network (CNN) classifier to achieve a high accuracy and a low manpower cost. The proposed two-layer CNN classifier designed based on the optimization hypothesis is evaluated and compared with other CNN classifiers. The DeepQuantify system adopting these CNN classifiers is evaluated for quantifying CD68-positive macrophages and 7/4-positive neutrophils and compared with the state-of-the-art deep learning segmentation architectures. DeepQuantify achieves an accuracy of 90.64% and 89.31% for CD68-positive macrophages and 7/4-positive neutrophils, respectively. The DeepQuantify system employing the proposed two-layer CNN architecture achieves better performance than those deep segmentation architectures. The quantitative analysis of two protein dynamics during muscle recovery is also presented.

show abstract

Detection of leukemia in microscopic white blood cell images

Cited by 40 publications

References 6 publications

Deep-Learning Based Label-Free Classification of Activated and Inactivated Neutrophils for Rapid Immune State Monitoring

Deep-Learning Based Label-Free Classification of Activated and Inactivated Neutrophils for Rapid Immune State Monitoring

Enhanced Support Vector Machine Based Leukaemia Cancer Classification

DeepQuantify: deep learning and quantification system of white blood cells in light microscopy images of injured skeletal muscles

Contact Info

Product

Resources

About